Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does most of it well: it discloses the return shape (injection_check with flagged, a risk enum, and signals), the heuristic caveat, billing behavior on failure ('failed reads are not charged'), and the exact cost ($0.003 USDC via x402). It does not cover auth requirements, rate limits, or latency overhead relative to read_url.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the differentiating clause, followed by detection details, then caveat and cost. No filler, and the highest-value information (how it differs from read_url) comes first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so describing the injection_check return object and its risk levels is exactly the right compensation, and pricing/billing behavior is covered. What is left implicit is the rest of the response payload, which is delegated entirely to the referenced sibling read_url.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter, and the schema already documents it fully (100% coverage: URI format, maxLength 2048, 'Public http(s) URL to read'). The description adds no additional constraint or format guidance beyond that, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb+resource and immediately differentiates from the sibling read_url by framing itself as 'Same as read_url plus a heuristic prompt-injection check'. The enumerated signals it detects make the added scope concrete, so an agent can distinguish it from read_url, read_pdf, or get_paper without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Same as read_url plus...' framing makes the selection condition clear: choose this over read_url when injection screening matters. It also states the 'heuristic, not a guarantee' limitation, which helps an agent decide whether to trust the flag. It stops short of an explicit when-not-to-use statement (e.g. that the check adds latency/cost versus plain read_url).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.